Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    building writer's block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    修士
    0.40
     docs
    0.37
    攀
    0.37
     Nationality
    0.36
     通販
    0.36
    副
    0.35
     SW
    0.35
    魧
    0.35
     Sekolah
    0.35
    )(&
    0.34
    POSITIVE LOGITS
     Leibn
    0.45
    interesse
    0.41
    ITTING
    0.40
    öy
    0.39
    odym
    0.39
    ugin
    0.38
    orin
    0.38
    édié
    0.38
    pared
    0.38
    shad
    0.38
    Act Density 0.000%

    No Known Activations